Innovations in Information and Communication Technologies (IICT-2020)

Today the online grocery shopping (OGS) is helping customers by making their life convenient by offering best and comfortable deals. Scope of online grocery shopping is increasing exponentially. Therefore, this study aims at examining the influencing role played by personal innovativeness (PI), economic values (EV), design aesthetic (DA), perceived enjoyment (PEJ) and convenience (CON) attributes on development of positive attitude to use OGS by Indian customers. For testing the variables and relationship of the proposed model, a structured questionnaire was formed and dispersed among 351 Ghaziabad and Delhi residents, out of which 232 were used for analysis. The Smart PLS 3.0 programme has been used to provide partial least square structural equation modelling (PLS-SEM) method. Finding a study easy to use (PEOU), perceived usefulness (PU), PI, EV, DA and PEJ and CON have a symbolic quantitative correlation in India with the acceptance of OGS. In contrast, PEJ did not support PEOU. Therefore, the study will provide direction to all online grocery service providers to design their services according to the customer’s expectation and need.

The role of digital technology in a company’s long-term development is to avoid undesirable experience in the normal situation and continue being competitive in forthcoming markets. The paper offers a comprehensive study on the role of digital technologies and its important impact on employees in the competitive world. A measure for the role of digital technologies and employee experience was built and tested for its reliability and validity. Descriptive statistics were used to understand the importance of digital technology and its impact on the employee experience in Indian firms. The results show that if a company has to thrive through these testing times, the only solution is through the integration of technology into their organizational structure. This has to be a permanent inclusion instead of a temporary solution for battling the side effects of the Covid-19 lockdown. The results also show that technological resolutions offer sustainable compensations across the business segments, and companies should emphasize investing in updating employee’s skill sets. Through the survey, it was also evident that organizations and institutions irrespective of their size or market share had to incorporate employee development including basic technological know-how apart from technical skill sets. These initiatives will help the organization and institutions to maintain their business models and profitability even in post-Covid times. Human resource practices backed by technology have enabled employees to lead a flexible life, grasp learning opportunities, stay safe, engaged, agile and motivated throughout the lockdown and quarantine periods.

Increasing engagement is a primary objective of organizations seeking to understand and measure engagement. Employee engagement is the extent to which employees feel connected, passionate about their duties at work and are committed and put unrestricted effort into their work. Employee engagement strategies have been proven to reduce staff turnover, improve productivity and performance, retain customers at a greater rate and make more profits. Employee engagement today has become interchangeable with terms like employee satisfaction and employee well-being. Professionals have a higher possibility to be “distracted” and “disengaged” at work in the dynamic workplace today. Most importantly, engaged employees have a sense of well-being and are happier both in their personal and in their professional lives. High levels of work engagement are when employees are involved with, committed to, enthusiastic, and passionate about their work. The objective of this research is to do a literature review and analyse the result that focuses on the evolving role of employee engagement practices in the dynamic workplace of today.

The university selection problem occurs when university prospects need to make college choices in the face of multiple universities based on preferences. University search web apps are decision support tools used by prospects to ease the search process. A review of such web apps revealed that these platforms were developed for universities in the USA and the UK and do not Nigerian Universities. In this paper, we propose UniversityCompass, an AHP-based ranking and selection app for prospects intending to study in Nigerian Universities. Since its live hosting, UniversityCompass.com had been assessed by over 1,000,000 users in more than 4,000,000 page views, which underscores its usefulness in aiding undergraduates prospecting of Nigerian Universities. We observed the highest spike in page views are the periods that coincides with peak of university search in the country, i.e. January. In addition, more than 85% of the respondents considered UniversityCompass as a suitable platform for university search and rated the app as either “very good” or “excellent”.

People management is a much challenging task nowadays. So practising employee experience and implementing them to their core will definitely bring positive results to experimental organizations. During COVID-19, it becomes a challenging task again when you give concern to productivity and cannot ignore your employee’s health and their safety equally to achieve your long-term goals. The objective of this research is to explore what employee experience practices in multinational organizations are practising and to analyse the impact of EE practices on psychological distance among employees during this dangerous pandemic. Our study considers advanced technology, strong communication, trust in leadership and health and well-being of the employees as the important drivers or dimensions of employee experience during COVID-19 phase. Also this study tries to communicate that by implementing these practices how multinationals have stepped forward to reduce psychological distance among their employees. The given scope for further studies could include quantitative testing of the developed model and also checking their effectiveness with respect to productivity of the firm.

Today’s world is facing digital revolution. The world has become a global village with the Internet connectivity. Business, corporate world, industries, media, educational institutes, and financial sector are all geared up for industrial and sectoral digitalization. Digital marketing and e-commerce have changed the business as usual communication caters to information and data exchange between individuals, groups as well as companies. Communication about sales, marketing, production as well as developments in various fields of digitalization is interrelated and dependent. This paper address the key connection between communication and digital culture, particularly in the present COVID-19 situation. Internet dependability for online education, digital banking transactions, and most IT companies allowing employees to work from home has become a new normal. This situation has created new challenges of maintaining seamless communication between stakeholders, vendors, clients, and society. IT companies, telecom sector, and apps supporting online ordering for groceries, vegetables, and medicines have demonstrated close relation between communication and digital platforms. This paper encompasses the roles, defines the key steps, and deals with opportunities and challenges faced by the stakeholders.

This is an empirical study which describes the financial issues with an increasing usage of the virtual currency in the present situation. With the introduction of the democratising, the influence of the ICT and its effect involved in various aspects of our lives like the economic, political, and the societal requirements. The financial frauds in various forms and its impact on financial market had been identified in the earlier research. The economic structure of the markets has been facilitating these. The frauds in the financial sector are identified as the lending frauds, identity frauds, and the investment frauds. The financial frauds are purely dependent on the market segmentation and the involvement of the various market instruments. The present study is carried out to understand the recent developments happening in the field of financial frauds, various developments like the free entry exit of participants, global currency involvement, increasing types of transactions in the financial sector, and the financial innovations involving technological and legal aspects. Technical problems in maintaining the secrecy and confidentiality of the dealings of the banking transactions. The present study tries to connect the different types of financial crimes to the facilities brought in by the ICT, and it needs more attention and more transparency to fight the white-collar crimes.

The greatest dare across the HR industry today across the globe is that they all have bulk numbers of resumes in their application tracking system (ATS) and customer relation management (CRM) systems, but filtering those resumes and mapping candidates to job openings from these systems manually plays a very tiresome task for recruiters. Finding qualified candidates from the applicant pool and fitting them in the right place is the key to successful recruiting. Technological innovations though help recruiters on a day-to-day basis, bringing out the most effective and efficient strategy is still a question. This is possible with the help of technology advancement in the form of artificial intelligence (AI) which could play a key role in making the recruitment process more operative. AI takes several forms, but this paper focuses on the role and impact of chatbots in recruitment industry. This study was conducted among 120 IT/ITES recruiters in South India. This paper highlights on the impact of an artificial intelligence chatbot on recruitment process. The authors have used correlational analysis and multiple regression analysis to test the facilitated hypothesis. This paper augments that artificial intelligence chatbots are very effective techniques which need to be implemented in recruitment process as it automates the whole process which eases the job of a recruiter. This study also details on the usage of various chatbots across the globe and its benefits for the recruitment process to be effective and efficient for the organizations to sustain in the competitive environment.

In modern times, especially in the current prevailing COVID-19 period, a system of studies came into the picture replacing the classroom learning with online classes. Although there are many challenges which the teachers and learners are facing during their online process of interaction, it has become the need of the hour. There may be various questions related to the online methods of teaching and learning such as the quality of online teaching, problems of students, the question of recognition, health issues, Internet connection, professional space, and still, its popularity is incredible. The online work environment now involves using communicative teaching tools and different software to interact with the learners as required. Microsoft Teams, Google Meet, Olympus, Zoom, and many more names are enlisted in the category of online assistance tools for academic advancement in the teaching–learning process. In the online mode of teaching, the teachers may choose their own schedules and timings, but is this flexibility adds to learning, or is it only a facility? Moreover, salaries for online instructors or teachers solely depend on the organization for which they are teaching, and it hardly matters what is their qualification and experience. It may be said that online teaching–learning provides a golden opportunity to meet people across the world while staying at home and it may be a rich experience for them to learn new things about the culture of other learners. They can share their way of life including their foods, clothes, behavior, etc., contributing to the mutual understanding and building global bridges: they can have a wonderful experience of all kinds of lifestyles.

Mobile phones or smart phones have changed or revolutionized the way we live. These days the short message service (SMS) is becoming fashionable. For spammers, the success of the mobile messaging channel has become a very attractive target to attack. To impose an additional level of security in the pervasive environment, we will create a system which is more authenticated for SMS. This system will have impact on user’s usability from the point of view of user’s safety. In modern era, the financial industries and other related agencies are seeing the SMS as an important aspect to communicate with their customers which somehow opens the easy flap for spammers, and customer’s safety measures is at hazard. The digital encryption methodologies are useful to support the SMS formation which needs two nodes to swap over digital signed SMS message. These two nodes are protected by the public key cryptography and authentication is done with the help of the ECDSA signature scheme. These two nodes are recognized as sender and receiver, and when a sender sends an SMS to any receiver, the unencrypted text is sent means that there is possibility of loss of information. In this paper, we propose the technique called Gaussian Naive Bayes Classification (GNBC) for the filtering of spam by SMS that solves the message topic model (MTM) problems. It is believed that some pre-processing rules and background terms make it the most appropriate model to completely represent spam by SMS. Finally, we have concluded that GNBC is more accurate for the SMS spam filtering activity.

Mathematical expression extraction is one of the most important challenges for decades, and hence, there is an extreme need to counter the issue of mathematical expression and concept retrieval from scientific documents. While there have been many attempts for mathematical expression (ME) retrieval by using diverse approaches like Symbol Layout Tree (SLT), DenseNet, convolution neural network (CNN), support vector machine (SVM) and many more. As a result, they lead to new implication and restrictions in precise ME similarity retrieval and its specific mathematical semantic. In order to analyze the mathematical document, the automatic detection and retrieval of similar recognized ME is a key task. The research paper presents the existing mathematical plagiarism detection techniques and mathematical expression extraction techniques proposed by different researchers. The prime objective of this research work is to propose an intelligent tool to filter the standard mathematical expression and notation from the scientific document.

Detecting lies is a challenging and necessary pursuit, with widespread implications in many scenarios, including police investigations, court decisions, and military circumstances. There are wide variety of techniques available for detecting deception. The most commonly being used is polygraph which is the oldest and traditional method for lie detection. Traditional-based lie detection methods require subjects to be tested which sometimes generate false positives when subject is anxious or aroused emotionally. Less work has been done to computationally and statistically predict lies. Hence, detection of lies is a prominent area that requires deliberations from the end of researchers, academicians and scientists to develop more automated systems based on subject’s emotions that not only offer reliability and accuracy but are also convenient for common man. This article aims to provide a comprehensive review of existing lie detection techniques and also proposes a novel approach based on subject’s emotion for lie detection.

There has been a tremendous growth in banking and finance sectors. With this growth, the ease to access of sanction loan has increased because many people are applying for loans. The problem here is that bank has only limited number of resources and capital, which the bank can distribute among the customers. The whole task of categorizing to whom the bank should sanction loan and to whom it should not has become a difficult task for the bankers. Generally, bank undergoes a rigorous procedure for verifying the customer to sanction loan. This procedure may take a week’s time or two. The drawback here is that the customer needs to wait for two whole weeks to know whether he/she is deserving or not. In this paper, we have reduced the risking factor of banks behind finding the appropriate person for loan approval by the bank. We even reduce the time of loan approval analysis. We first use data mining techniques to analyze previous records to which the bank has already sanctioned loan based on the analysis made out of these records we train the deep learning model. The new data is treated as testing data, and the output of the customer is calculated accordingly.

Load forecasting is the main exploration field in the smart grid technologies. The classification of load forecasting depends on its target forecasting that ranges from minutes to years. Residential smart home load forecasting focuses on forecasting energy consumption of smart homes which is crucial when it comes to energy conservation and load management issues. This paper focuses on application and implementation of deep learning algorithm known as long short-term memory (LSTM) that predicts the load of residence hours or days ahead and the time series load analysis of the houses will be presented.

In today’s world, the growth of population is increasing rapidly. As population increases the new problems are also generated. Advanced technology can solve these problems. Waste management is a big concern of today’s world. Traditional methods are failing now. Therefore, the problem of waste management also can be solved with the help of new technologies. This waste management can be done smartly with the help of a technology IoT. The main objective of this system is to create a solution for smart waste management which is smart dustbin. As waste is collected by municipal employees from the dustbins, but tracking the waste level manually in dustbin is very difficult and costly. In this case, when bin is filled, waste comes out from the bin and becomes the reason of serious health hazard to the surrounding environment. Smart dustbin provides the facility to track the status of bin waste. It is connected to the Internet; therefore, real-time information of dustbin can be received.

In the process of diagnosing a brain tumor, the most prominent task is the analysis of the MRI images, and so it is important to precisely assess the images. Despite advancements in the field of medical science and research, there are very few methodologies that provide us with accurate brain tumor segmentation. The segmentation of the images, which is done manually becomes a laborious, tedious task; moreover, the 3D nature of the data imposes several challenges in the segmentation of images, which is done in an automatic manner. Our research focuses on the approach for tackling the task of the segmentation by training a network architecture encouraged by U-Net. Worked on 2018 dataset of brain tumor segmentation challenge (BraTS), we got better results with our projected system than other state-of-the-art architectures like native U-Net architecture.

In recent times, Covid-19 has changed the dimensions of the educational industry. Universities across the global are focusing on the changing trends, technologies, and practices influencing the teaching and learning among teachers and students. This research paper mainly focuses on the emerging technologies in the Covid-19 providing about the real-time examples and insight the brief about the transformational shift how the universities are architect the various ecosystems both for instructors and learners. The relevant dataset of exam, quizzes, etc., from heterogeneous department were utilized for proposed methodology. The research work also includes the implications and challenges faced by the universities while implementing these technologies. The accuracy obtained was higher in the twenty-first century e-learning tools and lesser in all other cases as well as for the legacy system. The performance was observed, and various inferences were discussed with the effective delivery of the teaching material and their issues.

The escalating magnitude of data and its availability has raised a question on the trustworthiness of data. The solution to this problem lies in an effective discipline of study known as provenance. Data provenance provides the history and description of data to authenticate the genuineness and reliability of data, by attaching some extra information along with the original data which gives a description about its origin as well as transformation. The applications of provenance have stepped into the various arenas of practical fields. It has the potential to become a metrics of measuring data reliability, data quality, and data ownership and has gradually become one of the key aspects of various domains, for instance, business, science, and information technology. This paper will discuss the versatility of provenance and its applications in latest fields of research.

Today, the young mobile users are increasing day by day with more dependency on online retail apps. Therefore, this study aims to identify the influence of perceived incentive, perceived price, perceived information and customer relationship management to use food ordering apps. Using convenience sampling method, data of 174 young customers’ has been used to analyse through structural equation model analysis with the help of SmartPLS 2.0 and SPSS-20 software. Findings suggest that perceived incentives, perceived information and customer relationship management shows significant results while the perceived price shows insignificant result. Research suggests that the satisfaction and dissatisfaction level of the customer helps in enhancing their facility to use food ordering app. A customer always enjoys the facility of food ordering app, and customers always keep on changing with time and available technologies, motivate companies to continually offer new technologies and update their apps for providing better services.

Purpose This paper aims to understand the effect of enjoyment (ENJ), facilitating condition (FC), mobility (MOB), collaboration and trust in developing a positive attitude for Indian customers to use m-payment apps. Methodology The study proposed a new paradigm on the grounds of extended technology acceptance model (TAM). By using structural equation modeling (SEM), the frameworks were empirically examined on responses from 328 respondents. Findings—The empirical results indicate that five factors—collaboration, enjoyment, facilitating condition, mobility and trust, positively affect the consumer’s attitude for using m-payment services. However, it has been found that the collaboration and trust construct have no direct impact on the attitude to use m-payment apps. Research limitations/implications—The study highlights the significance of these other variables that are critical when it comes to using m-payment apps to identify buyer behaviour. The study will, therefore, guide for all m-payment service providers to develop their services accordingly.

This research article identifies the factors most needed to establish customer-centricity (CC) that convenience food customers most enjoy. The study collected primary data from 216 customers in India. In the study, potential variables were identified by concurrent research articles. This study identifies the factors required for customer-centricity and arranges them in order of priority, so that retailers can use them without any complexity. To develop such a model, the study has used the AHP tool. The study has classified the criteria of customer centricity into criteria and sub-criteria categories. Expanded food counters, attractive deals and discounts, store reputations and customer-oriented operations make convenience food retailing the main criteria for customer-centricity, while ambient, innovation, effective CRM as sub-criteria for customer-centricity. This study suggests that for convenience food retailing, retailers need to further empower these factors. Further studies on un-packaged food articles can identify more areas of improvement in existing food retail operations.

In India, banking sectors is facing a dynamic challenge regarding the base of customer base and its satisfaction. Quality in service or service is considered to be an important asset which helps in evaluation of customer satisfaction. Getting customer satisfaction can serve as a basis for customer retention. The banks are working hard to achieve customer satisfaction by providing high quality services. This study measures and compares customer perceptions on service quality of private sector and public banks using SERVQUAL model. For this research, the structured questionnaire was built and primary data have been collected using five different sections consisting of different questions. The study found that the service quality of private sector banks is working much better than public sector banks. The five parameters reliability(R), responsiveness (R), assurance (A), empathy (E) and tangibles (T) (RATER) for service quality for the bank were selected. The chi-square test was chosen to be applied for categorical variables where two variables are independent. The chi-square test was applied to all the parameters and the significant parameter was considered for further analysis for customer satisfaction

Educational studies usually correspond to routine teaching methods and textbook literature. Although as an essential process of making learning effective and exciting for students, it is considered that the classroom courses must involve interactive activities. Implementation of such interactive methods can be achieved by fusing playful classroom games, engaging the students with use of the latest methodologies, engaging the students with high enticement can make the course learning more interesting. In this new era of technology, games have grown prevalent in today’s media. Besides games, gamification is another trending technology in education, workplaces, business, etc. Gamification extends a simple way to motivate and promote learning and facilitate the development of sustainable life skills helping students to increase engagement in the learning process with creativity and imagination. Game elements in the form of game mechanics and dynamics act as motivators to achieve the desired goals. The findings in the educational contexts on the efficacy of gamification and game elements of this research achieved till date are concluded as carefully promising.

In modern times, pioneering works in the field of face recognition have seen the new development in biometric technology. A greater spectrum with modalities such as iris, face, fingerprints, signature, or hand has been largely deployed, and highly accurate systems using these modalities have been designed too. Recently, a critical issue has been addressed that affects the path of technological evolution in biometrics, i.e., spoofing, which is very resistant to biometric technology through external attacks. Spoofing is different from other IT security solutions as it is a purely biometric vulnerability. With the help of a sensor, an illegitimate user fools the biometric system by treating it as a genuine one using a synthetic forged version refers to as spoofing. The researchers and developers of the biometric community have worked a lot in suggesting and emerging different security methods. The main objective of this paper is to deliver an inclusive outline of the emerging field of anti-spoofing that has been carried out over the last decade. The work covers concepts, procedures, or advanced techniques that largely positioned face modality and also explains the future aspect in the field of biometric security.

An ongoing advancement in the condition of craftsmanship innovation assumes an imperative job in the picture handling applications, like biomedical, satellite picture preparing, artificial intelligence, object recognizable proof, diabetic retinopathy (DR), etc. DR is an eye disease found in people having high blood sugar. It can lead to loss of vision, if it is not treated properly. There is an increase in number of patients in comparison with ophthalmologists. The seriousness of the DR depends upon nearness of microaneurysms, hemorrhages, exudates and neovascularization. Specialists arrange diabetic retinopathy into five stages, namely ordinary, gentle, moderate, non-proliferative DR (NPDR) or proliferative DR (PDR). Convolutional neural network (CNN) results in high accuracy in classifying these diseases by spatial analysis. A CNN is progressively mind-boggling engineering construed more from the human visual perspective. A previous study done on DR suggests the use of CNN but with a different approach. Among other managed calculations involved, the proposed arrangement is to locate a superior and advanced way to classify the fundus picture with little pre-preparing techniques. Different fundus image databases available have been discussed. In this paper, different parameters used for the evaluation of developed systems have been presented.

Internet of things (IoT) has shown a different research direction in the domain of farming and agriculture. Smart agriculture has reduced the farmer’s effort and improved their capability in managing their crops, soil, water, field monitoring, pesticide control, etc. IoT-based solutions have increased the farmer’s attention toward humidity, temperature, pH value and environment conditions that are the most important concern in agriculture. The unique features of Internet of things like faster access to application and data, reduced human efforts, efficient communication and the global connectivity through different devices have made it a fast-growing technology in providing agriculture solutions. This paper explored various IoT smart agriculture systems and the challenges faced in deploying these systems.

Speech has been an integral part of human life acting as one of the five primitive senses of the human body. As such any software or application based upon speech recognition has a high degree of acceptance and a wide range of applications in defense, security, health care, and home automation. Speech is a waffling signal with varying characteristics at a high rate. When examined over a very short scale of time, it can be considered as a stationary signal with very small variations. In this paper, authors have worked upon the detection of a single user using multiple isolated words as speech signals. For designing the system, feature extraction using Mel-frequency cepstral coefficients (MFCCs) and feature matching using dynamic time warping (DTW) are considered as the designing of the system because of its simplicity and efficiency. Short-time spectral analysis is adopted which is the main part of the MFCC algorithm used in feature extraction. To compare any two signals varying in speed or having phase difference between them, DTW is used. Since two spoken words can never be the same, the DTW algorithm is best suited to compare two words.

As people age, their body tissues and organs begin to fail. This causes a number of diseases that can quickly destroy a person’s life. Thus, as long as they are alive, daily or weekly monitoring of the physiological body is an issue. To do this physically by visiting a hospital can be very difficult. IoT and smartphone-based systems are one subset of new technologies that focus on shifting in-hospital treatment to out-hospital treatment, therefore avoiding having to go to hospital to know his/her health status physically. The system collects real-time data from the patient’s body without burdening their daily activities. The practical implementation of the system is improved by taking five patients as a sample, and data acquired from each sensor is analysed by calculating the error rate. The advancement of information communication and technologies in mobile technology not only provides a calling service but provide services in health monitoring activities. This paper describes how advanced smartphones and wearable sensors play important functions in remote health monitoring. Wearable sensors can obtain data from the patient’s body, while smartphones can obtain the patient’s parameters (data) from wearable sensors through Bluetooth communication technology, and then send the data to a database (Cloud) through a wide area network (WLAN) technology for future access.

Effectiveness of the implementation of the hybrid lean six sigma (LSS) approach depends on the acceptance of the employees affected by this change. This context is crucial for changes in the organization of radical technological and innovative nature. McLean et al., (2017). Failure of continuous improvement initiatives in manufacturing environments: a systematic review of the evidence. Total Quality Management and Business Excellence, 28(3–4), 219–237.) indicate based on analysis of 72 journal articles selected; it is evident that continual improvement initiatives can fail due to a multitude of individual variables; hence, their implementation effectiveness is very important and of the moment from the point of view of management practice.The direct inspiration to use the TAM model to test the acceptance of the lean six sigma conception was its frequent use in the implemented ERP class systems (Bobek and Sternad, (2012). End user’s knowledge issues in ERP solutions use, Studies and Proceedings of Polish Association for Knowledge Management, no. 58, pp. 129–141. (It should be added at this point that the issue of supporting the lean six sigma concept by ERP class systems has been discussed in a paper presented at a conference scored by Springer—3rd International Conference on Microelectronics and Telecommunication Engineering ICMETE 2019 28 and 29 September New Delhi NCR Campus Ghaziabad India, the tile of the paper was—How much integrated ERP/MES/SCADA/ HMI systems support implementation of lean six sigma management concept? S. Świtek, L. Drelichowski, Z. Polkowski)), which are an example of information technology where the acceptance among users and the consolidation of employees’ attitudes are changes in cultural internal factors, including interactions in the field of external factors influencing an organization. The conducted pilot study allowed to define nine factors influencing acceptance for lean six sigma. They will be utilized in the main study, which will be elaborated in next paper.

It is obvious that the large scaled data can be generated as well as processed by implementing the most effective computational techniques. In this regard, applications inked to operation management, transact generation, health care as well as industrial applications require specific trends and patterns within these large socioeconomic datasets. Sometimes, it can be a point of discussion regarding specifying the parameters associated with the voluminous data to prioritize the granular information about the individual cluster. Also in many cases, emphasis can be given to analyze the social networks and social engagement behaviors of individuals by mapping mobility patterns implementing sensors or mechanisms as well as usage of remote sensors to track all the patterns provisioning the coordination with information communication. In some cases also, based on the web analytics along with machine learning, prediction associated with large scaled data invites the opportunities to new mechanisms with conceptual applications in management sector also. While concentrating on granular data, it is essential to entrust the key sources of the voluminous data whether private, public or self quantified. So adoption of the recent mechanisms can lead to generate ambient data which can partially be emitted to be linked with dynamic networks quantifying the actions and behaviors. It is observed that the size and dimension of data while associated and shared in business and general applications are enhanced immeasurably. The textual data may be structured or unstructured. Similarly, the images and social media sites linked to multiplicity platforms can be generated in voluminous structure to be the evident to strategic technology trends. Considering this trend, partially the machine learning techniques or evolutionary as well as heuristic techniques can be applied to prioritize and focus on the majority of data to overcome the specific challenges.

The intruder detection system plays a fundamental function in recognizing assaults in networks. To design an intelligent intruder detection system invites researchers from the machine learning domain to work in this area. With the availability of KDD99 datasets, some researchers encounter a class imbalance problem in it. This article performs a detailed empirical investigation of various resampling techniques to mitigate the effect of class imbalance. The study is performed on NSL-KDD multi-class datasets using fivefold cross-validation with G-Mean and AUC as evaluation metrics considering the decision tree as a classifier. The study inferred that the SMOTE technique performs well compared with the rest of the art.

The study identifies the key attributes considered by Indian consumers while purchasing private label brand (PLBs). It also studies the impact of identified psychographic and demographic attributes of consumers towards PLB purchase decision. The data was collected from 550 respondents through structured questionnaire from leading retailers of food and grocery as well as clothing and apparel segment in India. Initially, an exploratory factory analysis (EFA) was performed to identify psychographic attributes from consumer survey and different hypothesis framed was tested through multiple regression analysis and Chi square test. The results reveal brand consciousness, price consciousness, quality variability, store loyalty and consumers self-perception emerged as key psychological attributes followed by all socio-demographic factors, i.e. age, occupation, qualification, income and gender have significant impact on consumer PLB purchase decision. Based on the findings, PLB retailers were suggested to design an appropriate strategy to capture the market share of private label brands in Indian organised retail.

The COVID-19 now became a pandemic and rising rapidly and spreading in all parts of the world like fire. India reported its first COVID-19 case on January 30, when a student arrived in Kerala from Wuhan. Thousands of people are acquiring this deadly virus daily and with many people dying from it. The major concern of all the countries is to protect its citizens and try to eradicate this disease as fast as possible. This paper aims to perform exploratory analysis using the concepts of data science on the confirmed cases, total deaths, and total recovered cases of this virus. The research work predicts the spread of the outbreak for the next five days by using time-series forecasting algorithms. This paper deals with learning about how the corona virus is spreading and using that trend to predict for the upcoming days. It would be able to predict to a suitable accuracy which can help the government learn about the statistics of this disease and prepare further for protection against this. The results are discussed at last with prediction and error estimates.

The coronavirus epidemic is still on a surge and has harsh impacts on various factors across the globe including the economy and health. Though the recovery rate is also increasing, daily reporting cases are also increasing substantially. The best way till now is to take precautions and following the government guidelines. Till today, many different countries are line up to produce effective vaccination, but still, no such vaccine has completed its trial, and further, it will take a long time for the production and distribution among common citizens. We currently have a test process known as reverse transcription-polymerase chain reaction (RT-PCR) that is not reliable during the early stage of the disease. Also, a fast diagnosis is required as RT-PCR is time taking operation. Hence, imaging can be useful for the diagnosis as it can be quick and more reliable even in the early stage of the COVID-19 disease. Artificial techniques can be applied to radiological images such as CT scans and X-rays. In this article, we review the various research and responses in diagnosing the said disease using AI techniques on radiological images. Our findings suggest that using AI techniques like Convolution Neural Networks plays an important role in the diagnosing the COVID-19 by providing quick results and accuracy.

Robotics is the current growing technology with various applications in many fields practiced so far. The bit-by-bit strategies are assembled to know the growth of way arranging systems in different environmental situations and to spot the research gap. It reviews the most important contributions to the mobile robot path planning field from classical approach to heuristic approaches. The classical approaches include cell decomposition method, road map method, artificial potential field method; heuristic approaches such as genetic algorithm (GA), neural network (NN), ant colony optimization (ACO), and particle swarm optimization (PSO) are studied. Because of the numerous computational problems, heuristic methods outperformed the classical methods and gained great reputation. The navigation of static and dynamic surroundings is also examined and it has been remarked that the heuristic approaches have executed efficiently in all aspects when differentiated with classical methods. The paper ended up with tabular knowledge, and graphs analyzed the regularity of separate navigational policies which can be utilized for particular implementation during robot navigation.

Requirement prioritization (RP) is considered as an important phase of SDLC in the process of requirements engineering. Requirement prioritization techniques are very useful for making good decisions to determine the relative priority weights of the requirements as per their importance. The existing techniques are very complex and time consuming in fuzzy environment. FAHP is a very appropriate approach for RP. The FAHP has found its significant applications in today’s scenario and majority of the applications in requirement prioritization are derived by using EA and FPA and nonlinear techniques for fuzzy AHP priority derivation. However, FPA-based nonlinear approach is effective one but exhibits several issues of uncertainty and complexity. The performance of such prioritization approaches does not provide the appropriate priority as per the customer expectations, create multiple and conflict priority vectors, may result in different conclusions which are not acceptable to fuzzy pairwise comparison matrix. This research paper helps to overcome the issue of existing approach, proposes an effective and appropriate priority technique for fuzzy AHP called logarithmic fuzzy trapezoidal approach (LFTA) to conclude the priorities vector of requirements engineering. The proposed technique is used to resolve the typical gaps and meets the customer expectations of judgment making in real-life applications This technique is tested on real-life project ‘selection rank 1 of college’ based on different criteria’s.

India has been among the largest democracy around the world, and democratic election process has played an important role in achieving this status. Predicting elections result is an important factor as it influences the market situation at local and global level. This paper had focused on data analytics and machine learning using Python, on historical dataset. Historical datasets of Indian Parliamentary Elections have been taken for a larger time span of 1977–2014 and results of same have been plotted using Python. In this paper, five machine learning models have been used for predicting win or loss for a seat in an election. The models primarily used for this analysis are Gaussian Naive Bayes, extra tree classifier, K-nearest neighbors classifier (KNN), logistic regression and decision tree classifier. In result section, results of five model used for study were evaluated and compared. This study had depicted that decision tree classifier provided comparatively good accuracy score among the chosen five models.

In last few decades, data security has been a challenging issue to protect the copyright information and integrity of digital products. So digital watermarking is founded as one of the talented methods to defend digitized media. This paper defines functioning of major transform domain methods such as discrete cosine transform (DCT), quaternion Hadamard transform (QHT), discrete wavelet transform (DWT), discrete contourlet transform (DCT), and many more are discussed. Comparison of these techniques based on peak signal-to-noise ratio (PSNR) and normalized correlation (NC) is discussed in this paper. Various types of attacks are also evaluated on these techniques.

The recent advancements in artificial intelligence (AI) and digital transformation have led to a paradigm shift in the interact pattern of people with technology. With the adoption of artificial intelligence (AI) in all business processes, the biggest challenge being faced by organizations is the integration of artificial intelligence (AI) with emotional intelligence (EI). There is no denying the fact that as more and more technology is being involved, and it has become a two-way process. Human beings are trained to work with technology and the technology is taught to relate to people. An extensive secondary research is conducted to comprehend the digital transformations at workplace and explore the evolving concepts of AI and how will it connect with the emotions of the ‘Analog’ being applications. Through this paper, we will try to bring forth how artificial intelligence is being used as a support system to emotional intelligence and the emerging concept of emotion AI.

Supervised machine learning algorithms often suffer with overfitting during training steps which prevent it to perfectly generalizing the models. Overfitting is modelling concept in which machine learning algorithm models training data too well but not able to repeat the same accuracy on the testing data set. In this paper, we focus on regularization, which can help models to avoid overfitting problem with special focus on supervised learning algorithm, i.e. linear regression, logistic regression and neural network. Proposed regularization strategy guaranteed models performance and generalized for test data set by proper selection of features, and identifying less and more important features for data modelling purpose.

Reverse shell has now emerged as an effective tool used to penetrate systems and networks with speed and compromise them. The efficiency and robustness of reverse shell lie in its use of the victim’s machine to generate the connection request to the attacker. Unfortunately, this connection request goes unchecked by the host’s security systems as it originates from the host. To address this challenge, we present a typical reverse shell, its idea, its implementation including the model as well as how it works, how it infects the systems, and lastly, techniques with which we can prevent the reverse shell from infecting our systems and networks. It is coded in Python and implemented over Windows operating system, which gives this Shell an advantage because Python has various libraries which can control a significant number of aspects of any operating system. Exploiting this feature of the language, we have succeeded in building a reverse shell which gives the attacker complete control of the host the Shell has infected as well as the added functionality of uploading, downloading, and persistent backdoor creation. Furthermore, we present a technique which increases the robustness and functionality of our Shell and distinguishes it from other such similar programs.

Over the recent years, blockchain has emerged as an area of great interest with its applications in multiple domains like financial, technology, security, education, and many more. In addition to these, it also has a great potential to be used in many other areas and it is accompanied by other modern technologies like IoT, cloud computing, etc. In this time of global urbanization, a huge influx of people could be seen in the urban settings in pursuit of better career opportunities, health and education services and better standard of living. This has also tremendously increased the resource demands managing which could be a herculean task. A smart city could be considered as a modern digitized city which integrates the latest ICTs along with existing infrastructure to maximize the optimization of resource utilization to provide better quality of living with security and transparency. This paper aims to explore the potential and contribution of blockchain technology in smart cities along with IoT and provide a novel solution for easy and automated consumer utility payments based on smart contracts.

The article describes a part of implementation of the project, the purpose of which is to create a universal system for the recognition and analysis of human motor activity, based on inertial measurement units. Analysis of biometric features was conducted, and most informative and universal features that uniquely describe movements performed by a person in the course of everyday activity were identified. A method for identifying features using microelectromechanical inertial measuring units was proposed. A method for the formation of training examples for hybrid artificial neural networks was proposed. The classification of features depending on the dynamics and cyclicity was proposed. A method for automated feature extraction based on data threshold separation was proposed.

The bandwidth allocation and management which converges on efficient network performance is one of the important issues today in most of the organizations. The commercial service providers in this field are costly in terms of finance as well as time. This paper focuses on the development and customization of an open source application product “RadSense” over a network of two thousand nodes for a better network performance. The performance of the network is measured over a customized application which is further an integrated platform of open source applications pfSense and Radius. The development of this product has been done to reduce the cost of the commercial applications and high-end servers in the organizations. This paper also presents a study of network performance with properly managed data over an open source data base application “MySQL” on a low-end commodity server. Also, the integration of the different technologies over a newly developed application has come up with new dimensions in the field of open source firewall systems.

Wireless sensor network has significant applications but few flaws also exist. The flaw of sensor energy consumption requires to be tackled. The sensor is an integrated component of WSN that is used to collect data and then store within the data store. Sensors have limited energy associated with them. Conserving energy so that data collection can be prolonged is discussed through this paper. There are many mechanisms including LEACH, DEEC, MDEEC, EDEEC, etc., and all these mechanisms conserve energy but optimization in each protocol is missing. Problems associated with listed protocols are discussed, and mechanisms used to overcome the problems are also briefed. Nodes collaborating form clusters. Data transmission takes place from distinct clusters toward the base station. The energy of sensors needs to be preserved to enhance the lifetime of the network. This paper presents an overview of various existing metaheuristic techniques used to enhance the lifetime of the network. The multi-heuristic algorithms are chosen because it optimized energy of sensors or prevented from deterioration. The degradation is indicated in terms of packet drop ratio for determining network bandwidth. The analysis of some popular protocols has been done in this paper which can be used for future enhancements. DEEC protocol is best of all and can be used for optimization purposes. Energy efficiency predictions will be better in case sensors and can consume less energy.

The Internet of things (IoT) showed gigantic development in recent trends of industrial, medical and environmental applications. Due to the huge computational power in the cloud, opportunities for complete industrial device automation have emerged. The uninterrupted monitoring and beforehand fault detection of the machines build efficient process control in the automation process. Analysing data acquired from various IoT sensors with the help of suitable data processing algorithms combined with artificial intelligence (AI) can help achieve predictive maintenance of industrial equipment, production lines as well as home appliances. This will significantly help in improving the service life of appliances as well as reduce the servicing cost by diagnosing active faults. This research paper focuses on developing an IoT-based fault detection system by connecting various sensors to the equipment and capturing their data using the sensors and storing them in the cloud platform for further analysis. Further data analytics applied on the accumulated sensor data can be useful to carry out predictive maintainence of the equipment.

Text classification plays a vital role in many real-life applications. There are different methods for text classification primarily Naive Bayes classifier, support vector machine, etc. A good text classifier must efficiently classify large set of unstructured documents with optimal accuracy. Many techniques have been proposed for text classification. In this paper, we propose an integrated approach for text classification which works in two phases. In initial preprocess phase, we select the frequent terms and adjust the term weight by use of information gain and support vector machines. Second phase consists of applying Naïve Bayes classifier to the document vector. The experiment has been performed on the open research dataset of Forum of Information Retrieval (FIRE). In association rule, the correlation between data items is obtained with no requirement of external knowledge, whereas in classification, attention is given to small set of rules with the help of external knowledge. The proposed work uses FP-growth algorithm with absolute pruning for obtaining frequent text sets, and then, Naïve Bayes classifier model is used for training and constructing a model for classification. Our experimental result shows increase in efficiency while comparing with other traditional text classification methods.

A blockchain is a community ledger deal out in excess of a set-up that testimony operations (memorandums send commencing individual system knot to a further) carry out in the middle of network contributors. Every operation is confirmed by network nodes according to a mainstream agreement method prior to being added to the block chain. Recorded information is able to not be revolutionized or wipe away, and the past of each operation can exist re-formed by the side of in the least time. Authors have been proposed a system using block chain mechanism for health insurance entails institution of burly procedures for health data collection and compilation right from grass root level. The Recommended technique bestows the precise to the policyholder of health insurance to relocate the credit gained him for pre-existing conditions and time vault, keeping outs in case he chooses to switch the insurance provider.

The construction industry suffers from many unethical practices which lead to quality problems in the sector. With many clients dissatisfied with the workmanship of skilled labor, the study developed a web-based system to improve work ethics among skilled construction workers. The framework was developed using use case and system block diagram. In this study, HTML, CSS, MySQL and Java programming language were used in the design of the web-based system. The result was presented using screenshot. The designed interface includes the registration page, make request, make payment and rate the level of workmanship. With the introduction of the payment platform and rating system for skilled laborers, the work ethics is intended to be improved. This web-based system can be deployed by skilled labor outsourcing firms to enhance the work ethics of their skilled labor workers.

Information system drives every aspect of human endeavor, and it is a major stakeholder in human existence. Systems with poor modeling suffer a lot from poor implementation down to poor performance due to lack of critical subjection and testing. Software modeling is, therefore, of paramount importance in order to achieve a reliable system. There has been a lot of works done in software modeling, and eventually, the Universal Modeling Language was formulated to create a standard for software modeling. Although there have been some development or modeling tools that can be used to model a software system and the design then converted to software codes that can then be perfected, none of these tools has considered security and integrated as a single tool. Therefore, this paper focuses on building an integrated system (all-encompassing system) for building UMLsec-based modeled systems that will convert UML diagrams to code. The system integrates Eclipse Mars incorporated with Papyrus modeling plug-ins and Eclipse Kepler with Java EE incorporated with CARiSMA plug-ins. These four tools were integrated together by an executable application built with NetBeans. The system was tested by modeling an e-government system from the class diagram to analysis and code generation.

Inexhaustible grid interfacing framework is being elevated generally with a specific end goal to safe watch the utilization of ordinary sources of energy. Grid interconnection of high end inexhaustible sources with that of the grid causes unsettling influences and prompts the perpetual shutdown of the inverter. Customary controller, for example, linear controller and nonlinear controller perform well under adjusted state of activity; however, this controller ends up slow amid grid unsettling influences. Controller in view of AI techniques has been created in this way to deal with make the controller stable amid adjusted and un-adjusted state of activity. MATLAB Simulink-based framework has been created for checking the legitimacy of the proposed controller.

This paper deals with numerical investigation of two-phase dusty fluid under mixed convection flow. In the present research paper, it is proposed to investigate free forced convective boundary layer along with study and laminate floor for a spherical solid dust particle having uniform radius. Unique distinct parameter and its impact on the particle under different fluid condition surcharge temperature velocity effects have been presented. In order to solve the differential equation, all the governing equations were solved through finite difference method. It is observed that under interaction of different fluid particles the magnitude of velocity and temperature of the carrier fluid has been decreased to a great extent ultimately helping the magnitude of particle velocity and temperature to increase.

Arrhythmia and heart problems are one of the most important health problems in the whole world which leads to various other severe complications, for example, heart attack. As arrhythmia is a type of cardiologic disease, it can be used for pointing out the abnormality from normal heart activity and try to understand about heartbeat whether the heartbeat is normal or not. The main element that only a less number of people informed being discovered as a result of screening indicates that there are missing opportunities to prevent heart disease. There are different methods present for heart. Heart diseases are recognized by capturing information from patient’s body and forward results to doctors to reduce the risk of heart attack. So, the researcher always keeps trying to find out the best solution for this problem. The researchers have done huge research on this area, so according to the comparison between various techniques which are used for classification of arrhythmia, they prefer to use machine learning algorithm to achieve high performance and better accuracy.

Clustering is a process to form the same group as per the similarity values. Document clustering has given importance to the information retrieval and data mining process. This proposed work gives the improvement in efficiency and accuracy of the document clustering. This paper proposed a work which following phase: preprocessing, term document matrix and applying clustering algorithm. Initially, it shows flowchart and later calculates the TF, IDF and TF-IDF values. Later on, K-means clustering takes place to form the multiple clusters as per similarity measures. As per TF values of given keywords that show the 2D and 3D graphically representation.

Due to the development of faster and improved modes of communication, technologies, as well as customers, get benefited. The world is moving rapidly toward digitization, and connectivity has been placed under tremendous pressure. The development and implementation of IoT devices benefit all industry sectors, stimulating more areas in terms of convenience, productivity, and communication. But such a huge amount of data generated by IoT devices could result in a breakdown of IT infrastructure. To reach to the desired destination, this massive data travels via some intermediator. When the so-called intermediator that is cloud database is based in a remote location, the data can experience some kind of delay before it reaches the cloud for processing. So in recent years, the IT industry is attracted tremendous attention to improving communication between these technologies. And this is what the aim of edge computing (EC) is. Meanwhile also artificial intelligence (AI) algorithms and models have made breakthrough progress to accelerate the successful deployment of intelligence in the cloud services. By and large, AI services are executed in cloud for dealing with demands, because of the way that most AI models are intricate and difficult to process their induction results in favor of resource-limited devices. Nonetheless, such sort of ‘end–cloud’ architecture cannot address the issues of real-time AI services such as real-time analytics and smart manufacturing. Accordingly, deploying AI applications on the edge can widen the application situations of AI especially as for the low-latency characteristic. Combining the above two-mentioned paradigms, i.e., EC and AI can give rise to a new outlook: Edge Intelligence (EI). This paper provides insights into this new outlook by discussing core definitions, concepts, components, and frameworks. It also describes some necessary background in future research areas and challenges.

This article presents a robust image watermarking founded on discrete cosine transform (DCT), bi-dimensional empirical mode decomposition (BEMD) and particle swarm optimization (PSO). In encoding process, DCT coefficient is implemented on original image, and also, the BEMD decomposition is applied to disintegrate the watermark image. For the optimization, PSO is used for complex and multidimensional search. The embedding and scaling factor is embedded through the help of security key. Such a procedure is accompanied by the reverse of IDCT as well as IBEMD. Recovery algorithm is employed to extract the watermark image. The outcome of this technique shows that the suggested technique is robust compared to various different attacks. Therefore, this proposed technique is feasible for the visible quality of watermark image and improves the imperceptibility compared to other techniques.